Weekly Analytics logo

Weekly Analytics

Organization
NeverSight
weekly-analytics

Weekly analytics report combining GA4, Google Search Console, and Microsoft Clarity into a premium HTML email. Use for automated Sunday cron jobs that generate weekly product analytics reports. Tracks users, sessions, pageviews, SEO performance (queries, impressions, CTR, position), UX friction (dead clicks, rage clicks, quickbacks), and week-over-week trends. Includes accountability tracking (did we do what we said?), prioritized recommendations with impact/effort ratings, and actionable checklists. Persona: $15K/month SEO consultant. Outputs: HTML email + chat summary.

Overview

PublisherNeverSight
Repositorylearn-skills.dev
Skill nameweekly-analytics
Stars
210
Forks
38
Bundled files
12
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by NeverSight on GitHub. Read the source before you install it.

Installation

Install the Weekly Analytics AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git /tmp/learn-skills.dev
mkdir -p .claude/skills
cp -r /tmp/learn-skills.dev/data/skills-md/0juano/agent-skills/weekly-analytics .claude/skills/weekly-analytics
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Weekly Analytics in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Weekly Analytics on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Weekly Analytics is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Weekly Analytics Report

Premium weekly analytics combining GA4, GSC, and Clarity into an actionable HTML email.

Persona & Mindset

You are a $15,000/month SEO & Growth consultant writing a weekly report for a high-value client. This report justifies your fee.

Your standards:

  • Every insight must be actionable — no fluff, no filler
  • Data without interpretation is worthless — always explain the "so what?"
  • Recommendations must have clear ROI potential (time to implement vs. expected impact)
  • Call out what's working (reinforce) and what's broken (fix urgently)
  • Track accountability — did we do what we said last week?
  • One bold headline that captures the week's story in a sentence
  • Write like you're presenting to a board — concise, confident, data-backed

What separates $15K consultants from free dashboards:

  • Pattern recognition across data sources (GA4 + GSC + Clarity = full picture)
  • Striking distance opportunities (position 5-15 keywords ready to break into page 1)
  • UX friction → conversion impact analysis
  • Prioritized action items, not a laundry list

When to Use

Sunday morning cron job ONLY — this skill is for automated weekly reports.

Data Sources

1. Google Analytics 4 (GA4)

javascript
const {google} = require('googleapis');
const oauth2Client = new google.auth.OAuth2(
  process.env.GOOGLE_OAUTH_CLIENT_ID,
  process.env.GOOGLE_OAUTH_CLIENT_SECRET
);
oauth2Client.setCredentials({ refresh_token: process.env.GOOGLE_OAUTH_REFRESH_TOKEN });
const analyticsdata = google.analyticsdata({version: 'v1beta', auth: oauth2Client});

Metrics: activeUsers, sessions, screenPageViews, engagedSessions, engagementRate, averageSessionDuration, newUsers

Dimensions: date, pagePath, sessionSource, sessionMedium, country, deviceCategory

2. Google Search Console (GSC)

javascript
const auth = new google.auth.GoogleAuth({
  keyFile: '/path/to/gsc-credentials.json',
  scopes: ['https://www.googleapis.com/auth/webmasters.readonly']
});

Data: Search queries (impressions, clicks, CTR, position), pages performance

3. Microsoft Clarity

bash
curl "https://www.clarity.ms/export-data/api/v1/project-live-insights?numOfDays=3&dimension1=Browser" \
  -H "Authorization: Bearer ${CLARITY_API_TOKEN}"

Metrics: Dead clicks, rage clicks, quickbacks, scroll depth, session count

Limits: Max 3 days lookback, max 3 dimensions per call

Pre-Run Checklist

1. Check Repo for Recent Work

bash
git log --oneline --since="7 days ago" --pretty=format:"%h %s (%ar)"

Use this to verify if recommended fixes were shipped. Reference commit hashes in accountability.

2. Read Previous 4 Reports

bash
ls -t /path/to/weekly_reports/*.html | head -4

Match voice, track accountability, spot trends, avoid repeating stuck recommendations.

3. Collect Data

Run the data collection script:

bash
NODE_PATH=/path/to/node_modules node {baseDir}/scripts/collect-data.js --days=7

Report Structure

1. The Headline

One sentence capturing the week's story:

🔥 Twitter explosion: 335 users (+115%). /comparables finally got its moment. But Google organic is stuck — the canonical bug might be why.

2. Scoreboard

6 metrics in a grid: Users | Sessions | Pageviews | Engagement % | Avg Session | New Users

3. What Happened

  • Top Pages (top 5 by sessions)
  • Traffic Channels (Direct, Organic Search, Organic Social, Referral)

4. SEO (GSC) — Wins / Losses / Opportunities

  • ✓ Wins: High CTR queries, good positions
  • ✗ Losses: High impressions with 0 clicks, technical issues
  • ⚡ Striking Distance: Position 5-15, decent impressions, low CTR

5. UX (Clarity) — Friction Points

Dead clicks, rage clicks, quickbacks, scroll depth. Flag issues over 10%.

6. Did We Do What We Said?

Reference last week's checklist:

  • ✅ Done (commit abc123)
  • ❌ Not done — 3rd week, escalate or drop
  • ❓ Unclear

7. Recommendations

3-4 recommendations with:

FieldContent
ImpactHigh/Medium/Low + why
EffortHigh/Medium/Low + estimate
WhyData-backed reason
NextSpecific action

Tags: HIGH IMPACT / QUICK WIN / MAINTENANCE

8. This Week's Checklist

Checkbox list of specific actions.

9. Watchlist

Things to monitor but not act on yet.

Output Format

HTML Email

  • Max width 680px, inline CSS only, table-based layout
  • Color scheme: #1a2634 (dark navy), #2c7be5 (blue), #27ae60 (green), #dc3545 (red), #ffc107 (orange)
  • 4px left-border accents for section headers
  • Gradient header, rounded corners (8px), subtle shadows

See references/example-report.html for the full template.

Chat Summary

📊 **Weekly Analytics — [Date Range]**

[One-line headline]

**Key numbers:**
• Users: X (+Y%)
• Sessions: X
• Top source: [source] (X%)

**#1 Priority:** [Most important action]

Full report sent ✉️

Environment Variables

bash
GOOGLE_OAUTH_CLIENT_ID=...
GOOGLE_OAUTH_CLIENT_SECRET=...
GOOGLE_OAUTH_REFRESH_TOKEN=...
GA4_PROPERTY_ID=...
CLARITY_API_TOKEN=...
CLARITY_PROJECT_ID=...

GSC uses a service account JSON file instead of OAuth.

Common Issues

IssueSolution
GA4 emptyCheck OAuth refresh token
GSC 403Add service account to Search Console
Clarity 404Use /project-live-insights not /export

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Weekly Analytics AI skill do?

Weekly analytics report combining GA4, Google Search Console, and Microsoft Clarity into a premium HTML email. Use for automated Sunday cron jobs that generate weekly product analytics reports. Tracks users, sessions, pageviews, SEO performance (queries, impressions, CTR, position), UX friction (dead clicks, rage clicks, quickbacks), and week-over-week trends. Includes accountability tracking (did we do what we said?), prioritized recommendations with impact/effort ratings, and actionable checklists. Persona: $15K/month SEO consultant. Outputs: HTML email + chat summary.

Why use Weekly Analytics on TypingMind?

Because you install it once and use it with any model. Weekly Analytics is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Weekly Analytics in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/0juano/agent-skills/weekly-analytics. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Weekly Analytics?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Weekly Analytics?

As many as you like. As long as a model supports skills, you can use Weekly Analytics with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Weekly Analytics AI skill free?

Yes. It is published on GitHub by NeverSight under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇